Cascaded Feedforward Neural Networks for speaker identification using Perceptual Wavelet based Cepstral Coefficients.
G. RenishaT. JayasreePublished in: J. Intell. Fuzzy Syst. (2019)
Keyphrases
- speaker identification
- feedforward neural networks
- speech signal
- mel frequency cepstral coefficients
- speech recognition
- gaussian mixture model
- neural network
- speaker recognition
- back propagation
- feature extraction
- noisy environments
- wavelet transform
- automatic speech recognition
- multiresolution
- broadcast news
- image compression
- audio signal
- non stationary
- multilayer perceptron
- hidden layer
- wavelet domain
- artificial neural networks
- low level
- feature vectors
- mixture model
- em algorithm
- multiscale
- pattern recognition
- speaker diarization